IEEE Transactions on Emerging Topics in Computational Intelligence最新文献_第2页

Neighbor-Embedded Graph Neural Network-Based Crowd Delivery Traffic Management in Smart City 基于邻域嵌入图神经网络的智慧城市人群输送交通管理

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2026-03-16 DOI: 10.1109/TETCI.2026.3670691

Kishu Gupta;Deepika Saxena;Ashutosh Kumar Singh;Chung-Nan Lee

{"title":"Neighbor-Embedded Graph Neural Network-Based Crowd Delivery Traffic Management in Smart City","authors":"Kishu Gupta;Deepika Saxena;Ashutosh Kumar Singh;Chung-Nan Lee","doi":"10.1109/TETCI.2026.3670691","DOIUrl":"https://doi.org/10.1109/TETCI.2026.3670691","url":null,"abstract":"The significant upsurge in vehicle traffic presents a considerable challenge in the pursuit of smart mobilization and transportation (SMT) worldwide.Current approaches primarily focus on vehicular traffic management through congestion prediction but fall short in addressing essential objectives such as traffic reduction and appropriate vehicle selection to alleviate congestion in smart cities (<inline-formula><tex-math>$SmCt$</tex-math></inline-formula>). To address these concerns, this work introduces a novel <italic>Neighbor-Embedded Graph Neural Network-based Crowd Delivery Traffic Management</i> (NeCDM) Model, comprising two key components: the Traffic Congestion Prediction Unit (TCPu) and the Traffic Observation and Management Unit (TOMu). The TCPu utilizes Graph Neural Network (GNN) optimization to accurately predict traffic flow levels at various delivery stations within <inline-formula><tex-math>$SmCt$</tex-math></inline-formula> ecosystems. Additionally, the TOMu facilitates the intelligent selection of the most suitable delivery vehicles for fulfilling crowd delivery requests (<inline-formula><tex-math>$CDR$</tex-math></inline-formula>). This work emphasizes the potential of crowd delivery as a feasible solution for achieving SMT goals while adhering to smart city parameters (<inline-formula><tex-math>$mathcal {SCP}$</tex-math></inline-formula>s), such as reduced carbon emissions, shorter travel times, and minimized travel distances. The proposed model achieves notable improvements in computational efficiency, including reductions of up to 4.03% in L1 loss (<inline-formula><tex-math>$pounds$</tex-math></inline-formula>), 16.66% in L2 loss (<inline-formula><tex-math>$pounds_{rmse}$</tex-math></inline-formula>), and 7.64% in computation time.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 3","pages":"2391-2403"},"PeriodicalIF":6.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148508766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Memory-Based Deep Reinforcement Learning for Quantum Control With Partial Observations 基于记忆的量子控制深度强化学习

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2025-11-28 DOI: 10.1109/TETCI.2025.3631693

Haixu Yu;Qi Yu;Chunlin Chen;Xudong Zhao

{"title":"Memory-Based Deep Reinforcement Learning for Quantum Control With Partial Observations","authors":"Haixu Yu;Qi Yu;Chunlin Chen;Xudong Zhao","doi":"10.1109/TETCI.2025.3631693","DOIUrl":"https://doi.org/10.1109/TETCI.2025.3631693","url":null,"abstract":"Deep reinforcement learning (DRL) has gained increasing attention in quantum physics, especially for quantum control problems, as it effectively handles high dimensionality and complex dynamics. However, many existing DRL-based quantum control methods assume full observability of quantum states, which tends to be impractical due to the massive state copies required for precise quantum measurements. To address this, we model quantum control under partial observations and introduce a memory-based DRL (MDRL) method that efficiently handles such scenarios. The proposed MDRL comprises two key components: a memory-based exploration strategy and a memory-based reward scheme. Specifically, the agent is equipped with a biology-inspired brain to memorize information derived from partial observations, including whether an episode is successful and the number of steps spent on a successful episode. The exploration strategy leverages the memorized information to guide interactions with the quantum system, while the reward scheme assigns appropriate rewards, together enabling the agent to learn an effective control strategy. The effectiveness of MDRL is verified by three examples, i.e., one-qubit state control, two-qubit state control, and <inline-formula><tex-math>$T_{x}$</tex-math></inline-formula> gate design. Numerical results demonstrate that MDRL outperforms several representative DRL algorithms for quantum control.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 3","pages":"2220-2234"},"PeriodicalIF":6.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Homophone-Based Chinese Natural Language Data Augmentation 基于同音字的汉语自然语言数据增强

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2026-03-03 DOI: 10.1109/TETCI.2026.3655163

Jia Wei;Xingjun Zhang;Witold Pedrycz;Longxiang Wang;Weiping Ding;Xuehai Qian

{"title":"Homophone-Based Chinese Natural Language Data Augmentation","authors":"Jia Wei;Xingjun Zhang;Witold Pedrycz;Longxiang Wang;Weiping Ding;Xuehai Qian","doi":"10.1109/TETCI.2026.3655163","DOIUrl":"https://doi.org/10.1109/TETCI.2026.3655163","url":null,"abstract":"Data, devices, and algorithms drive progress in artificial intelligence, and high quality data is essential for model training. However, collecting and labeling such data is costly. Inspired by computer vision, natural language data augmentation has attracted attention as a way to expand corpora through random insertion, deletion, synonym replacement, swapping, and large language model based generation. Most Chinese augmentation methods still follow English style strategies and fail to exploit Chinese specific linguistic properties, which limits their usability and effectiveness. Chinese users often make homophone errors in instant messaging programs such as QQ, WeChat, and WhatsApp. However, readers can still understand the intended meaning from context, background, and language habits. We call this phenomenon homophone consistency. We exploit Chinese homophone consistency for Chinese natural language data augmentation and design a Homophone-based Chinese Augmentation. HCA converts a sentence into a pinyin queue and then converts the pinyin queue back into a sentence using a dictionary based dynamic programming algorithm for pinyin identification. Words in the original sentence are replaced with homophones with a specified probability. HCA broadens Chinese augmentation using Chinese features, enriches the Chinese data augmentation strategy space, and provides a reference for designing language specific augmentation methods for other languages. We fine tune Chinese BERT on four datasets of different sizes and evaluate test accuracy. HCA improves test accuracy by up to 37.62% when the dataset is small and improves it by 3.42% on average. We also conduct ablation studies to analyze the effects of key parameters on training outcomes.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 3","pages":"2291-2300"},"PeriodicalIF":6.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148514412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Guest Editorial: Special Issue on Quantum Computing Meets Computational Intelligence: A New Vision for Smart Systems 特刊：量子计算与计算智能：智能系统的新愿景

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2026-03-28 DOI: 10.1109/TETCI.2026.3691548

Giovanni Acampora;Autilia Vitiello;Rebing Wu;Bing Xue;Gary Yen

引用次数: 0

Spatio-Temporal Series Prediction Based on Multi-Objective Evolutionary Deep Convolutional Echo State Networks 基于多目标进化深度卷积回声状态网络的时空序列预测

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2026-03-25 DOI: 10.1109/TETCI.2026.3670634

Meiling Xu;Lixin Tang;Lu Chen

{"title":"Spatio-Temporal Series Prediction Based on Multi-Objective Evolutionary Deep Convolutional Echo State Networks","authors":"Meiling Xu;Lixin Tang;Lu Chen","doi":"10.1109/TETCI.2026.3670634","DOIUrl":"https://doi.org/10.1109/TETCI.2026.3670634","url":null,"abstract":"Accurate prediction of spatio-temporal series remains a challenging task due to complex spatial dependencies, temporal dynamics, and factors such as data sparsity, nonlinearity, and high dimensionality. To address these challenges, this paper proposes a novel framework which integrates a spatio-temporal interpolated deep convolutional echo state network with an improved multi-objective evolutionary algorithm. The model integrates cubic spline interpolation to enhance temporal resolution, a spatial attention mechanism to capture inter-location correlations, and a convolution-based deep echo state network to efficiently model spatio-temporal patterns. A multi-objective evolutionary algorithm is then employed to jointly optimize model hyper-parameters with two objectives of maximizing prediction accuracy and minimizing model complexity. To further improve efficiency, a topological data analysis-based strategy is used to select a representative and diverse subset of candidate solutions, reducing computational cost without compromising optimization quality. Experiments on two real-world meteorological datasets demonstrate that the proposed approach achieves superior prediction accuracy across single and multiple horizons. Ablation study further confirms the importance of each architecture component and the effectiveness of the proposed optimization strategy. The results validate the potential of the proposed model as an efficient tool for real-world spatio-temporal forecasting tasks.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 3","pages":"2361-2375"},"PeriodicalIF":6.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148508755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient Evolutionary Neural Architecture Search Using Reliable Fitness Evaluations for Image Classification 基于可靠适应度评价的高效进化神经结构搜索用于图像分类

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2025-09-03 DOI: 10.1109/TETCI.2025.3602074

Gonglin Yuan;Bing Xue;Mengjie Zhang

{"title":"Efficient Evolutionary Neural Architecture Search Using Reliable Fitness Evaluations for Image Classification","authors":"Gonglin Yuan;Bing Xue;Mengjie Zhang","doi":"10.1109/TETCI.2025.3602074","DOIUrl":"https://doi.org/10.1109/TETCI.2025.3602074","url":null,"abstract":"Neural Architecture Search (NAS) has gained considerable attention for automating the design of Deep Neural Networks (DNNs) and reducing human effort. However, most NAS algorithms require substantial computational resources. One-shot NAS mitigates this by training a large supernet, allowing candidate architectures to inherit weights, but these methods remain computationally intensive and may lead to unreliable performance evaluations. To address these challenges, we propose an efficient one-shot NAS method with reliable fitness evaluations. Our approach employs a novel weight initialization strategy tailored to the supernet's architecture, significantly reducing training time. During the evolutionary search process, the supernet is fine-tuned based on the candidate architectures being evaluated, ensuring more accurate performance estimations. Furthermore, a robust population initialization method is introduced for the Genetic Algorithm (GA), leveraging insights from supernet training to guide the search process effectively. Experimental results demonstrate that our method achieves error rates of 2.59%, 16.67%, and 23.9% on CIFAR10, CIFAR100, and ImageNet, respectively, while requiring only 0.31, 0.28, and 4.1 GPU-days. Compared with those competitors, our approach offers a favorable trade-off between performance and computational cost. Additional analyses confirm the robustness and efficiency of the proposed supernet training, population initialization, and fine-tuning techniques.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 3","pages":"2276-2290"},"PeriodicalIF":6.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148513371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Reinforcement Learning-Assisted Automated Operator Portfolio for Constrained Multi-Objective Optimization 约束多目标优化的深度强化学习辅助自动算子组合

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2026-03-13 DOI: 10.1109/TETCI.2026.3670673

Shuai Shao;Ye Tian;Shangshang Yang;Xingyi Zhang

{"title":"Deep Reinforcement Learning-Assisted Automated Operator Portfolio for Constrained Multi-Objective Optimization","authors":"Shuai Shao;Ye Tian;Shangshang Yang;Xingyi Zhang","doi":"10.1109/TETCI.2026.3670673","DOIUrl":"https://doi.org/10.1109/TETCI.2026.3670673","url":null,"abstract":"Constrained multi-objective optimization problems (CMOPs) are of great significance in the context of practical applications, ranging from scientific to engineering domains. Most existing constrained multi-objective evolutionary algorithms (CMOEAs) usually employ fixed operators all the time, which exhibit poor versatility in handling various CMOPs. Therefore, some recent studies have focused on adaptively selecting the best operators for the current population states during the search process. The evolutionary algorithms proposed in these studies learn the value of each operator and recommend the operator with the highest value for the current population, resulting in only a single operator being recommended at each generation, which can potentially lead to local optima and inefficient utilization of function evaluations. To address the dilemma in operator adaptation, this paper proposes a reinforcement learning-based automated operator portfolio approach to learn an allocation scheme of operators at each generation. This approach considers the optimization-related and constraint-related features of the current population as states, the overall improvement in population convergence and diversity as rewards, and different operator portfolios as actions. By utilizing deep neural networks to establish a mapping model between the population states and the expected cumulative rewards, the proposed approach determines the optimal operator portfolio during the evolutionary process. By embedding the proposed approach into existing CMOEAs, a deep reinforcement learning-assisted automated operator portfolio based evolutionary algorithm for solving CMOPs, abbreviated as CMOEA-AOP, is developed. Empirical studies on 33 benchmark problems demonstrate that the proposed algorithm significantly enhances the performance of CMOEAs and exhibits more stable performance across different CMOPs.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 3","pages":"2348-2360"},"PeriodicalIF":6.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148516180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding SpikeSMOKE：基于交叉尺度门控编码的单目3D目标检测的脉冲神经网络

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2026-03-16 DOI: 10.1109/TETCI.2026.3670672

Xuemei Chen;Huamin Wang;Jing Peng;Hangchi Shen;Shukai Duan;Shiping Wen;Tingwen Huang

{"title":"SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding","authors":"Xuemei Chen;Huamin Wang;Jing Peng;Hangchi Shen;Shukai Duan;Shiping Wen;Tingwen Huang","doi":"10.1109/TETCI.2026.3670672","DOIUrl":"https://doi.org/10.1109/TETCI.2026.3670672","url":null,"abstract":"With the wide application of 3D object detection in some fields such as autonomous driving, its energy consumption is constantly increasing, making the research on low-power consumption alternatives a key research area. The spiking neural networks (SNNs), possessing low-power consumption characteristics, offer a novel solution for this research. Consequently, we apply SNNs to monocular 3D object detection and propose the SpikeSMOKE architecture, which represents a new attempt at low-power monocular 3D object detection. It’s well known that the discrete signals of SNNs can lead to information loss compared to artificial neural networks (ANNs), which limits their feature representation capabilities. To solve this problem, inspired by the synaptic filtering mechanism of biological neurons, we propose a new Cross-Scale Gating Coding Mechanism (CSGC), which can enhance feature representation by combining cross-scale fusion of attentional methods and gated filtering mechanisms. In addition, to reduce the computation and accelerate training, we present a novel light-weight residual block that can maintain spiking computing paradigm and the highest possible detection performance. Our method is effective on the KITTI, NuScenes-mini and CIFAR10/100 datasets. Compared to the baseline SpikeSMOKE under the 3D Object Detection, the proposed SpikeSMOKE with CSGC can achieve 11.78 (+2.82, Easy), 10.69 (+3.2, Moderate), and 10.48 (+3.17, Hard) on the KITTI autonomous driving dataset by <inline-formula><tex-math>$AP|_{R_{11}}$</tex-math></inline-formula> at 0.7 IoU threshold, respectively. It is worth noting that the results of SpikeSMOKE can significantly reduce energy consumption compared with the results of SMOKE. And SpikeSMOKE-L (lightweight) can further reduce the amount of parameters by 3 times and computation by 10 times compared to SMOKE.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 3","pages":"2404-2415"},"PeriodicalIF":6.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148508768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advancing Privacy and Accuracy With Federated Learning and Homomorphic Encryption 通过联邦学习和同态加密提高隐私和准确性

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2026-03-16 DOI: 10.1109/TETCI.2026.3670702

Quoc Bao Phan;Dinh C. Nguyen;Thinh T. Doan;Tuy Tan Nguyen

引用次数: 0

Interpretable and Adaptive Graph Contrastive Learning With Information Sharing for Biomedical Link Prediction 基于信息共享的生物医学链接预测的可解释自适应图对比学习

IF 6 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2026-06-01 Epub Date: 2025-10-27 DOI: 10.1109/TETCI.2025.3616045

Junkai Liu;Le Zhang;Yijie Ding;Prayag Tiwari;Xiaoyi Guo;Weiping Ding

{"title":"Interpretable and Adaptive Graph Contrastive Learning With Information Sharing for Biomedical Link Prediction","authors":"Junkai Liu;Le Zhang;Yijie Ding;Prayag Tiwari;Xiaoyi Guo;Weiping Ding","doi":"10.1109/TETCI.2025.3616045","DOIUrl":"https://doi.org/10.1109/TETCI.2025.3616045","url":null,"abstract":"The identification of unobserved links in drug-related biomedical networks is essential for various drug discovery applications, which is also beneficial for both disease diagnosis and treatment through exploring the underlying molecular mechanisms. However, existing solutions face significant challenges due to three main limitations, i.e., (1) lack of interpretability to provide comprehensive and reliable insights, (2) insufficient robustness and flexibility in cold-start scenarios, and (3) inadequate interaction and sharing of multi-view information. In light of this, we propose DrugXAS, an interpretable and adaptive cross-view contrastive learning framework with information sharing for biomedical link prediction. Specifically, DrugXAS has three distinctive characteristics for addressing these challenges. To solve the first problem, we propose an attention-aware augmentation scheme to provide understandable explanations of intrinsic mechanisms. To deal with the second challenge, we propose an adaptive graph updater and neighborhood sampler, which select proper neighbors according to the feedbacks from the model to improve aggregation ability. To tackle the third issue, an information sharing module with diffusion loss is proposed to incorporate chemical structures into heterogeneous relational semantics and facilitate the contrast process. Empirically, extensive experiments on seven benchmark datasets involving multi-type tasks demonstrate that DrugXAS outperforms the state-of-the-art methods in terms of precision, robustness, and interpretability.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"10 3","pages":"2332-2347"},"PeriodicalIF":6.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0